(2 min)
Existing person re-identification (Re-ID) works mostly consider a short-term
search problem assuming unchanged clothes and personal appearance. However, in
real-world we often dress differently across locations, time, dates, seasons,
weather, and events. As a result, the existing methods are unsuitable for
long-term person Re-ID with clothes change involved. Whilst there are several
recent long-term Re-ID attempts, a large realistic dataset with clothes change
is lacking and indispensable for enabling extensive study as already
experienced in short-term Re-ID setting. In this work, we contribute a large,
realistic long-term person identification benchmark. It consists of 178K
bounding boxes from 1.1K person identities, collected and constructed over 12
months. Unique characteristics of this dataset include: (1) Natural/native
personal appearance (e.g., clothes and hair style) variations: The
clothes-change and dressing styles all are highly diverse, with the reappearing
gap in time ranging from minutes, hours, and days to weeks, months, seasons,
and years. (2) Diverse walks of life: Persons across a wide range of ages and
professions appear in different weather conditions (e.g., sunny, cloudy, windy,
rainy, snowy, extremely cold) and events (e.g., working, leisure, daily
activities). (3) Rich camera setups: The raw videos were recorded by 17 outdoor
security cameras with various resolutions operating in a real-world
surveillance system for a wide and dense block. (4) Largest scale: It covers
the largest number of (17) cameras, (1, 121) identities, and (178, 407)
bounding boxes, as compared to alternative datasets. Our dataset and benchmark
codes are available on https://github.com/PengBoXiangShang/deepchange.